AI brief
A Q&A post on AI Stack Exchange discusses types of delay in reinforcement learning, namely observation delay, action delay and reward delay, and asks about an unclear case.
Written by AI from AI Stack Exchange's published text.
Source
“According to the question in How to deal with the time delay in reinforcement learning? , we can tell the delay in the reinforcement learning can be observation delay, action delay and reward delay.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗